Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 814 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.0442. Min Range: -4.0442

Max Act: 4.0337. Min Act: -0.1700

Data Index: 160108 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.0442. Min Range: -4.0442

Max Act: 4.0337. Min Act: -0.1700

Data Index: 6132102 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.0442. Min Range: -4.0442

Max Act: 4.0442. Min Act: -0.1700

Data Index: 8728261 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.9814. Min Act: -0.1700

Data Index: 887087 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.9850. Min Act: -0.1700

Data Index: 8628246 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.9850. Min Act: -0.1700

Data Index: 6691672 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.9850. Min Act: -0.1700

Data Index: 8758233 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.9850. Min Act: -0.1700

Data Index: 5453166 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.9421. Min Act: -0.1700

Data Index: 1456768 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.9306. Min Act: -0.1700

Data Index: 4727469 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.9351. Min Act: -0.1700

Data Index: 3248353 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.9413. Min Act: -0.1700

Data Index: 7032207 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.9539. Min Act: -0.1700

Data Index: 7524722 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.9306. Min Act: -0.1700

Data Index: 2573104 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.9386. Min Act: -0.1700

Data Index: 1863229 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.9086. Min Act: -0.1700

Data Index: 1893513 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.8975. Min Act: -0.1700

Data Index: 6515430 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.8977. Min Act: -0.1700

Data Index: 3166407 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.9208. Min Act: -0.1700

Data Index: 5500787 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.0442. Min Range: -4.0442

Max Act: 3.8920. Min Act: -0.1700

Data Index: 8406701 (Open Web Text)

Max Activating Token Index: 16